Ethics, Fairness & Safety

The Mascot’s Code. At year’s end, Chibany audits what the campus systems actually learned — and writes a code of conduct for machines that learn from people. Can the kiosk be fooled with a sticker? Is the cafeteria recommender fair to every dorm — and what would “fair” even mean, stated as a conditional probability? Whose priors did the models inherit from their data? And when we trained the robot trainee with rewards, what did we actually teach it?

graph LR
    A[Adversarial<br>Examples 🤖] --> B[Fairness<br>Formalisms]
    B --> C[Bias in Data]
    C --> D[Alignment<br>& Safety]

Part in preparation

These chapters accompany Week 12 of the Human and Machine Learning course and are being written now. The stubs below sketch each chapter’s premise.

Chapters

Adversarial Examples
Fairness, Formally
Bias in Data
Alignment & Safety

This project is generously funded by the Japanese Probabilistic Computing Consortium Association (JPCCA).